Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7109
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and specific court-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tramonto
    -0.46
    muka
    -0.45
    伏
    -0.44
     plainte
    -0.43
     Piac
    -0.41
     Daher
    -0.41
    говор
    -0.41
     speciali
    -0.41
     ſever
    -0.41
     Rumuni
    -0.40
    POSITIVE LOGITS
    Tikang
    0.85
    TagMode
    0.81
    ⓧ
    0.75
    GraphicsUnit
    0.75
    iss
    0.74
     ModelExpression
    0.74
    ształ
    0.70
    :+:
    0.70
    WriteBarrier
    0.70
     AssemblyCulture
    0.68
    Activations Density 1.906%

    No Known Activations